用嵌入空间密度评估图像分类模型置信度，提升准确率。
Prior Distribution and Model Confidence
- 通过测试样本与训练数据在嵌入空间的距离估算置信度。
- 过滤低密度预测后，分类准确率显著提升。
- 无需重训练，适用于多种模型和跨领域应用。
我们研究了训练数据分布对图像分类模型置信度与性能的影响。提出一种模型无关的框架——嵌入密度（Embedding Density），通过测量测试样本在嵌入空间中与训练分布的距离来估计预测置信度，无需重新训练。通过过滤低密度（低置信度）预测，该方法显著提升分类准确率。我们在多种模型架构上评估了嵌入密度，并与当前最先进的分布外（OOD）检测方法进行了比较。该方法具有潜在的跨领域通用性。
原文摘要 · Abstract (English)
We study how the training data distribution affects confidence and performance in image classification models. We introduce Embedding Density, a model-agnostic framework that estimates prediction confidence by measuring the distance of test samples from the training distribution in embedding space, without requiring retraining. By filtering low-density (low-confidence) predictions, our method significantly improves classification accuracy. We evaluate Embedding Density across multiple architectures and compare it with state-of-the-art out-of-distribution (OOD) detection methods. The proposed approach is potentially generalizable beyond computer vision.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。